bytedance-iaas / splitwise-demosLinks
☆26Updated 3 months ago
Alternatives and similar repositories for splitwise-demos
Users that are interested in splitwise-demos are comparing it to the libraries listed below
Sorting:
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆87Updated last month
- KV cache store for distributed LLM inference☆269Updated 3 weeks ago
- The driver for LMCache core to run in vLLM☆42Updated 4 months ago
- PyTorch distributed training acceleration framework☆49Updated 4 months ago
- ☆50Updated 3 months ago
- A lightweight design for computation-communication overlap.☆143Updated last week
- ☆58Updated 4 years ago
- A low-latency & high-throughput serving engine for LLMs☆380Updated 3 weeks ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- NVIDIA Inference Xfer Library (NIXL)☆422Updated this week
- Efficient and easy multi-instance LLM serving☆437Updated last week
- ☆86Updated 3 months ago
- Stateful LLM Serving☆73Updated 3 months ago
- ☆73Updated 2 months ago
- ☆37Updated 6 months ago
- DeepSeek-V3/R1 inference performance simulator☆149Updated 3 months ago
- ☆28Updated 2 months ago
- Microsoft Collective Communication Library☆64Updated 7 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆100Updated last year
- NCCL Profiling Kit☆138Updated 11 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆80Updated last month
- ☆69Updated last week
- ☆29Updated 4 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆246Updated 2 weeks ago
- ☆90Updated 5 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆117Updated last year
- ☆96Updated 9 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆42Updated last month